agrawal-priyank / machine-learning-classification Goto Github PK

• Implemented logistic regression with l2 regularization and stochastic gradient descent optimization to build a linear classifier for classifying positive and negative reviews using the Amazon Baby Products Reviews dataset.
• Plotted the precision and recall trade-off against different threshold values for a review to be labeled as positive.
• Implemented decision trees with ADA boosting to classify safe and risky loans using the Loan Lending Club dataset.

1. Linear Classifier
2. Linear Classifier Learning (Logistic Regression)
3. Linear Classifier Regularization
4. Decision Trees
5. Decision Tree with Implementation
6. Decision Tree with Overfitting
7. Boosting
8. ADA Boosting using Decision Stumps
9. Precision and Recall
10. Stochastic Learning

Python

Anaconda, Graphlab Create Installation guide

Jupyter notebook (IPython)

1. Fork this repository to have your own copy
2. Clone your copy on your local system
3. Install necessary packages

This repository does not contain optimal machine learning models! It only assesses various models that can be built using different machine learning algorithms (either implemented or used directly from Graphlab Create package) to perform different tasks.